Enhancing Single-Frame Supervision for Better Temporal Action Localization.

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it requires only one annotated frame per action. However, it often suffers from poor performance due to the lack of precise boundary annotations.

Knowledge Conditioned Variational Learning for One-Class Facial Expression Recognition.

The openness of application scenarios and the difficulties of data collection make it impossible to prepare all kinds of expressions for training. Hence, detecting expression absent during the training (called alien expression) is important to enhance the robustness of the recognition system. So in this paper, we propose a facial expression recognition (FER) model, named OneExpressNet, to quantify the probability that a test expression sample belongs to the distribution of training data.

Exploring High-order Spatio-temporal Correlations from Skeleton for Person Re-identification.

Person re-identification (Re-ID) has become a hot research topic due to its widespread applications. Conducting person Re-ID in video sequences is a practical requirement, in which the crucial challenge is how to pursue a robust video representation based on spatial and temporal features. However, most of the previous methods only consider how to integrate part-level features in the spatio-temporal range, while how to model and generate the part-correlations is little exploited.

Graph Learning on Millions of Data in Seconds: Label Propagation Acceleration on Graph Using Data Distribution.

Graph-based semi-supervised learning methods have been used in a wide range of real-world applications, e.g., from social relationship mining to multimedia classification and retrieval.

Exploring complex and heterogeneous correlations on hypergraph for the prediction of drug-target interactions.

The continuous emergence of drug-target interaction data provides an opportunity to construct a biological network for systematically discovering unknown interactions. However, this is challenging due to complex and heterogeneous correlations between drug and target. Here, we describe a heterogeneous hypergraph-based framework for drug-target interaction (HHDTI) predictions by modeling biological networks through a hypergraph, where each vertex represents a drug or a target and a hyperedge indicates existing similar interactions or associations between the connected vertices.

Cost-Sensitive Hypergraph Learning With F-Measure Optimization.

The imbalanced issue among data is common in many machine-learning applications, where samples from one or more classes are rare. To address this issue, many imbalanced machine-learning methods have been proposed. Most of these methods rely on cost-sensitive learning.

[Case control study on anatomical locking plate and ordinary steel plate for the treatment of closed calcaneal fracture with SandersⅡand Ⅲ].

Objective: To compare clinical efficacy between anatomical locking plate (ALP) and ordinary steel plate (OSP) in treating closed calcaneal fractures with SandersⅡ and Ⅲ.

Methods: From May 2016 to May 2018, 68 patients with closed Sanders typeⅡ and Ⅲ calcaneal fractures were retrospectively analyzed, and were divided into anatomical locking plate group (ALP group) and ordinary steel plate group (OSP group) according to two kinds of plate fixation, and 34 patients in each group. In ALP group, there were 21 males and 13 females aged from 20 to 63 years old with average of (35.

View-Aware Geometry-Structure Joint Learning for Single-View 3D Shape Reconstruction.

Reconstructing a 3D shape from a single-view image using deep learning has become increasingly popular recently. Most existing methods only focus on reconstructing the 3D shape geometry based on image constraints. The lack of explicit modeling of structure relations among shape parts yields low-quality reconstruction results for structure-rich man-made shapes.

Hypergraph Learning: Methods and Practices.

Hypergraph learning is a technique for conducting learning on a hypergraph structure. In recent years, hypergraph learning has attracted increasing attention due to its flexibility and capability in modeling complex data correlation. In this paper, we first systematically review existing literature regarding hypergraph generation, including distance-based, representation-based, attribute-based, and network-based approaches.

Effect of intensity-modulated radiation therapy on sciatic nerve injury caused by echinococcosis.

Conventional radiotherapy has a good killing effect on femoral echinococcosis. However, the sciatic nerve around the lesion is irreversibly damaged owing to bystander effects. Although intensity-modulated radiation therapy shows great advantages for precise dose distribution into lesions, it is unknown whether intensity-modulated radiation therapy can perfectly protect the surrounding sciatic nerve on the basis of good killing of femoral echinococcosis foci.

Kullback-Leibler Divergence Metric Learning.

The Kullback-Leibler divergence (KLD), which is widely used to measure the similarity between two distributions, plays an important role in many applications. In this article, we address the KLD metric-learning task, which aims at learning the best KLD-type metric from the distributions of datasets. Concretely, first, we extend the conventional KLD by introducing a linear mapping and obtain the best KLD to well express the similarity of data distributions by optimizing such a linear mapping.

CPS-Based Self-Adaptive Collaborative Control for Smart Production-Logistics Systems.

Discrete manufacturing systems are characterized by dynamics and uncertainty of operations and behavior due to exceptions in production-logistics synchronization. To deal with this problem, a self-adaptive collaborative control (SCC) mode is proposed for smart production-logistics systems to enhance the capability of intelligence, flexibility, and resilience. By leveraging cyber-physical systems (CPSs) and industrial Internet of Things (IIoT), real-time status data are collected and processed to perform decision making and optimization.

Correntropy-Induced Robust Low-Rank Hypergraph.

Hypergraph learning has been widely exploited in various image processing applications, due to its advantages in modeling the high-order information. Its efficacy highly depends on building an informative hypergraph structure to accurately and robustly formulate the underlying data correlation. However, the existing hypergraph learning methods are sensitive to non- Gaussian noise, which hurts the corresponding performance.

Hypergraph-Induced Convolutional Networks for Visual Classification.

At present, convolutional neural networks (CNNs) have become popular in visual classification tasks because of their superior performance. However, CNN-based methods do not consider the correlation of visual data to be classified. Recently, graph convolutional networks (GCNs) have mitigated this problem by modeling the pairwise relationship in visual data.

Inductive Multi-Hypergraph Learning and Its Application on View-Based 3D Object Classification.

The wide 3D applications have led to increasing amount of 3D object data, and thus effective 3D object classification technique has become an urgent requirement. One important and challenging task for 3D object classification is how to formulate the 3D data correlation and exploit it. Most of the previous works focus on learning optimal pairwise distance metric for object comparison, which may lose the global correlation among 3D objects.

IPAD: Intensity Potential for Adaptive De-Quantization.

Display devices at bit depth of 10 or higher have been mature but the mainstream media source is still at bit depth of eight. To accommodate the gap, the most economic solution is to render source at low bit depth for high bit-depth display, which is essentially the procedure of de-quantization. Traditional methods, such as zero-padding or bit replication, introduce annoying false contour artifacts.

Intermediate-calcium based cementitious materials prepared by MSWI fly ash and other solid wastes: hydration characteristics and heavy metals solidification behavior.

Municipal solid waste incineration (MSWI) fly ash is a by-product of garbage incineration power generation, and its disposal is currently a world problem because it contains over standard heavy metals. This research aims to solidify the heavy metals in MSWI fly ash and make it to be utilizable construction materials under the guidance of intermediate-calcium cementitious materials (ICCM), and meanwhile figure out the solidification and hydration mechanism. The hydration characteristics of ICCM were characterized by XRD, FTIR, Si MAS-NMR and SEM techniques, and the environmental properties are investigated by TCLP and EPMA.

Beyond Pairwise Matching: Person Reidentification via High-Order Relevance Learning.

Person reidentification has attracted extensive research efforts in recent years. It is challenging due to the varied visual appearance from illumination, view angle, background, and possible occlusions, leading to the difficulties when measuring the relevance, i.e.

Three-dimensional conformal intensity-modulated radiation therapy of left femur foci does not damage the sciatic nerve.

During radiotherapy to kill femoral hydatid tapeworms, the sciatic nerve surrounding the focus can be easily damaged by the treatment. Thus, it is very important to evaluate the effects of radiotherapy on the surrounding nervous tissue. In the present study, we used three-dimensional, conformal, intensity-modulated radiation therapy to treat bilateral femoral hydatid disease in Meriones meridiani.

[Case-control study on the clinical characteristics of senile-osteoporotic Colles fracture].

Objective: To analysis and compare the clinical characteristics of Colles fractures between patients with osteoporotic and without osteoporotic.

Methods: From June 2007 to June 2009, 260 patients with Colles fracture were reviewed, including 60 males and 200 females, with a mean age of 66.5 years old.

[Assessment of percutaneous vertebroplasty and percutaneous kyphoplasty for treatment of senile osteoporotic vertebral compression fractures].

Objective: To investigate the clinical effects and safety of vertebroplasty and kyphoplasty for the senile osteoporotic vertebral compression fractures.

Methods: From December 2004 to June 2008, 28 patients (40 vertebrae) with osteoporotic vertebral compression fractures were treated with percutaneous vertebroplasty (PVP group), there were 11 males (14 vertebrae) and 17 females (26 vertebrae), with an average age of 72 years (ranged, 70 to 91 years). The fracture site of vertebral body was from T5 to L5.